Rumor: DeepSeek trained a 3T-parameter model but held back over serving economics

zephyr_z9 · x · 2026-09-10

teortaxesTex claims DeepSeek was working on a 3T-parameter backbone model (possibly with an extra 1T-param Engram, his speculation) but wasn't sure it would be economical to post-train and serve; something will come once their clusters grow. Quoted takes speculate a 2T+ param V4.5 Pro and frontier-level pricing near $5/M tokens.

Related event: Rumor: DeepSeek Trained a 3T-Parameter Model but Held Back Release(3 posts)→

Original post →

More from Models

Models channel →